I am a second-year PhD student at Simon Fraser University, advised by Yasutaka Furukawa. Previously, I graduated from Carnegie Mellon University with BSc in Electrical & Computer Engineering, where I was advised by Kris Kitani.
I am interested in computer vision, deep learning and machine learning. My research focus is understanding structured geometry data such as CAD, building and floorplan.
I serve as reviewer for NeurIPS, ECCV, ICML, 3DV.
Using disentangled codebooks to generate diverse and high-quality CAD models, enhances user control, and enables efficient exploration of the CAD design space.
A new explore-and-classify framework for structured architectural reconstruction from aerial image.
Monocular video dataset with ground truth annotations of 3D object pose, shape and part motion. We leverage 3D human pose for more accurate inference of the object spatial layout and dynamics.
Treat single-cycle image translation as modules that can be used recurrently where the process is bounded by mutual information constraints between the input and output images.
Use the Hamming bound to derive optimal criteria for learning hash codes with a deep network.